Senior AI Engineer

Salary: £25,000 - 65,000 per year

Requirements:

• We require 2+ years of hands-on experience building and productionizing LLM applications.
• We require deep technical knowledge of vector databases such as Qdrant, Weaviate, Pinecone, or pgvector, and orchestration layers such as LangGraph or LlamaIndex.
• We require experience working with heterogeneous documents such as PDFs.
• We require experience with re-ranking models.
• We require strong software engineering fundamentals and deep experience in asynchronous programming with asyncio and FastAPI.
• We require experience handling highly concurrent, I/O-bound LLM and database calls.
• We require proven experience solving production RAG challenges such as context window management, metadata filtering, and semantic routing.
• We require experience leveraging coding harnesses such as Claude Code.
• We require mastery of Git, automated testing, and CI/CD pipelines.
• We require experience working with cloud platforms such as AWS.
• We require the ability to rapidly prototype an approach, validate it with metrics, and pivot fast in a fast-moving environment.

Responsibilities:

• We design and develop reusable, scalable AI platform services that expose GenAI models, knowledge retrieval pipelines, and agent workflows to application teams.
• We build and maintain knowledge retrieval systems.
• We process heterogeneous documents like PDFs and build embedding pipelines that extract, chunk, and embed content into embedding models.
• We make content from unstructured documents AI-ready by optimizing structure, removing ambiguity, and embedding machine-readable metadata.
• We set up frameworks for monitoring and evaluating AI output quality, including relevance, accuracy, safety, drift, and cost.
• We build platform observability for latency, cost, and usage.
• We act as a centre of excellence for the business on the technical side of AI and LLM usage, setting best practices and accelerating adoption.
• We create governance layers for PII redaction, prompt filtering, and related guardrails.

Technologies:

• AI
• AWS
• asyncio
• CI/CD
• Claude Code
• Cloud
• Embedding Models
• FastAPI
• Git
• LLM
• RAG
• API
• Fine-tuning
• LESS
• Neo4J
• Python
• vLLM

More:

We are Octopus Energy UK, working from London in a full-time hybrid setup. Our mission is to use technology to accelerate the transition to a low-carbon future, and we built Kraken from scratch to power our platform and serve over 70 million households. We have been using GenAI in live customer-facing environments since 2022 and are now scaling our AI capabilities across the business. We offer a flexible approach to salary discussions, strong benefits, and a culture built on autonomy, learning, and impact. We have been recognised as one of the UKs top companies to work for, including a top ten ranking in the Sunday Times Best Places to Work 2024, and we provide an inclusive hiring process with accommodations available on request.

last updated 34 week of 2026